Interested in the differences in strategic behavior between humans and LLMs? Come chat with me and @caroline-wang.bsky.social this Thursday afternoon, 5pm, #ICML2026 poster session in Hall A (Poster #401)!

Caroline Wang@caroline-wang.bsky.social · 7mo ago

[1/n] Just wrapped up 7 months interning with @pcastr.bsky.social at Google DeepMind and I'm so excited to share our work: arxiv.org/abs/2602.10324. TLDR: We used LLM-powered program synthesis to automatically model and discover differences between human and LLM strategic behavior

SWC & @gatsbyucl.bsky.social are inviting expressions of interest from early career researchers seeking to establish an independent research group in mechanistic theories of neural computation or learning via external fellowship. Please share with your networks and colleagues! Apply by 16 July.

Fellowship Sponsorship | Sainsbury Wellcome Centre

The Sainsbury Wellcome Centre for Neural Circuits and Behaviour & Gatsby Computational Neuroscience Unit, University College London, are looking to sponsor early career researchers in theoretical or c...

sainsburywellcome.org

6/14 ATLAS designs experiments with intricate temporal structures—like overlapping reward blocks—which force competing models to maximally reveal their differences. Notice how the block durations are precisely tailored to the hypotheses at hand!

14/14 By linking data-driven hypothesis generation with hypothesis-driven experiment selection, ATLAS shows real potential to accelerate the discovery of interpretable insights in cognitive science and beyond. Read the full paper here: arxiv.org/abs/2606.12386

ATLAS: Active Theory Learning for Automated Science

Advancing scientific understanding through mechanistic modeling requires posing the right experimental questions to yield maximally informative data. To automate this pursuit within cognitive science,...

arxiv.org

New work on automated (interpretable!!) experimental design, led by @noemielteto.bsky.social See 👇 for thread

Noémi Éltető@noemielteto.bsky.social · 3mo ago

First paper since joining Google DeepMind! We present 🌍ATLAS (Active Theory Learning for Automated Science), a pipeline that generates interpretable mechanistic models from data and optimizes experiments to test them. Thread below

Data-driven model discovery 🔁 Model-driven experiment selection. For mechanistically-interpretable models! From Google DeepMind Neuroscience Lab, let by @noemielteto.bsky.social

Noémi Éltető@noemielteto.bsky.social · 3mo ago

First paper since joining Google DeepMind! We present 🌍ATLAS (Active Theory Learning for Automated Science), a pipeline that generates interpretable mechanistic models from data and optimizes experiments to test them. Thread below

New work from the Google DeepMind neurolab, led by @neurokim.bsky.social and @kevinjmiller.bsky.social. We use an LLM-based approach to discover new cognitive models of animal reward learning. More info in the 🧵.

Kevin J Miller@kevinjmiller.bsky.social · 3mo ago

Computational models are a key part of science but discovering new ones is hard! DataDIVER discovers concise models from data, which surface new mechanistic ideas and clear predictions for future experiments From Google Deepmind Neuroscience Lab + collaborators www.biorxiv.org/content/10.6...

I have been so excited about this project. In many ways the most surprising thing to me was how seemingly similar the AI-discovered models were to simple ones I thought I understood, even though they fit way better. This means we can also really get what makes them work.

Kevin J Miller@kevinjmiller.bsky.social · 3mo ago

Computational models are a key part of science but discovering new ones is hard! DataDIVER discovers concise models from data, which surface new mechanistic ideas and clear predictions for future experiments From Google Deepmind Neuroscience Lab + collaborators www.biorxiv.org/content/10.6...

New preprint! Very excited to share our new work introducing DataDIVER, for automatically discovering interpretable computational models from scientific data 📊🤿 See below for a visual summary from my magnificent co-lead @kevinjmiller.bsky.social ! 👇

Kevin J Miller@kevinjmiller.bsky.social · 3mo ago

Computational models are a key part of science but discovering new ones is hard! DataDIVER discovers concise models from data, which surface new mechanistic ideas and clear predictions for future experiments From Google Deepmind Neuroscience Lab + collaborators www.biorxiv.org/content/10.6...

really proud of this work done with fantastic collaborators, in particular daniel, @kevinjmiller.bsky.social & @neurokim.bsky.social ! i learned so much about neuroscience, & it was great to work on using AI techniques to advance science. read kevin's thread below or, even better, read the paper!

Kevin J Miller@kevinjmiller.bsky.social · 3mo ago

Computational models are a key part of science but discovering new ones is hard! DataDIVER discovers concise models from data, which surface new mechanistic ideas and clear predictions for future experiments From Google Deepmind Neuroscience Lab + collaborators www.biorxiv.org/content/10.6...

Computational models are a key part of science but discovering new ones is hard! DataDIVER discovers concise models from data, which surface new mechanistic ideas and clear predictions for future experiments From Google Deepmind Neuroscience Lab + collaborators www.biorxiv.org/content/10.6...

Excited to launch Principia, a nonprofit research organisation at the intersection of deep learning theory and AI safety. Our goal is to develop theory for modern machine learning systems that can help us understand complex network behaviors, including those critical for AI safety and alignment. 1

News from central Jersey: I'm running to represent New Jersey's 12th Congressional District. By entering the fray, I hope to bring ideas of repairing our frayed republic. Not only to defend it in 2026, but to build something stronger, for generations to come! samwang.substack.com/p/entering-t...

Wanna compare dynamics across neural data, RNNs, or dynamical systems? We got a fast and furious method🏎️ The 1st preprint of my PhD 🥳 fast dynamical similarity analysis (fastDSA): 📜: arxiv.org/abs/2511.22828 💻: github.com/CMC-lab/fast... I’ll be @cosynemeeting.bsky.social - happy to chat 😉

1. New preprint resolving a conundrum in systems neuroscience with an AI scientist, and humans Reilly Tilbury, Dabin Kwon, @haydari.bsky.social, @jacobmratliff.bsky.social, @bio-emergent.bsky.social, @carandinilab.net, @kevinjmiller.bsky.social, @neurokim.bsky.social www.biorxiv.org/content/10.1...

Characterizing neuronal population geometry with AI equation discovery

The visual cortex contains millions of neurons, whose combined activity forms a population code representing visual stimuli. There is, however, a discrepancy between our understanding of this code at ...

biorxiv.org

Associate Professor/Professor of Cognitive Neuroscience job opening in our own @imagingneuroucl.bsky.social department. Details here: www.ucl.ac.uk/work-at-ucl/...

UCL – University College London

UCL is consistently ranked as one of the top ten universities in the world (QS World University Rankings 2010-2022) and is No.2 in the UK for research power (Research Excellence Framework 2021).

ucl.ac.uk

I am so honoured to have been selected as one of the Jane Coffin Childs Fund fellows this year!

Jane Coffin Childs Fund for Medical Research@jcchildsfund.bsky.social · last yr.

We're thrilled to announce the 2025 class of Jane Coffin Childs Fellows! See our latest blog post and "look book" to learn more about our newest Fellows and their exciting research! www.jccfund.org/blog/the-jan... www.jccfund.org/wp-content/u...

Very pleased to share our recent work, in which we use LLMs for automated discovery of interpretable models of animal behavior 🪰🐀🕵️‍♀️ that take the form of Python programs 🐍 See below for a summary of key results by @pcastr.bsky.social!

Pablo Samuel Castro@pcastr.bsky.social · 2y ago

Can LLMs be used to discover interpretable models of human and animal behavior?🤔 Turns out: yes! Thrilled to share our latest preprint where we used FunSearch to automatically discover symbolic cognitive models of behavior. 1/12

Cognitive models of behavior are a key part of neuroscience. But discovering them is hard! In new work from Google DeepMind Neuroscience and collaborators @hhmijanelia.bsky.social, we demonstrate an approach that uses LLMs and large datasets to discover models automatically.

Pablo Samuel Castro@pcastr.bsky.social · 2y ago

Can LLMs be used to discover interpretable models of human and animal behavior?🤔 Turns out: yes! Thrilled to share our latest preprint where we used FunSearch to automatically discover symbolic cognitive models of behavior. 1/12

one of the most intriguing projects i've been involved in: automated scientific discovery in an area (human/animal RL) I've been working on forever. can an LLM do the job of my grad students? if it is backed up by super smart scientists incl @pcastr.bsky.social @neurokim.bsky.social & kevin miller

Pablo Samuel Castro@pcastr.bsky.social · 2y ago

Can LLMs be used to discover interpretable models of human and animal behavior?🤔 Turns out: yes! Thrilled to share our latest preprint where we used FunSearch to automatically discover symbolic cognitive models of behavior. 1/12